© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 111114
    Prev
    Next
    INDEX
    Explanations

    references to financial or operational aspects of businesses and their effects on jobs and community welfare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    adequate or sufficient

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    とにかく
    -0.38
     specifically
    -0.38
     specific
    -0.35
    Specifically
    -0.33
     càng
    -0.33
    越来越
    -0.33
    specifically
    -0.32
    どうしても
    -0.32
    IImage
    -0.31
    特定的
    -0.31
    POSITIVE LOGITS
     comfortably
    1.05
     raisonnable
    0.91
     adequately
    0.88
     reasonably
    0.88
     sufficient
    0.83
     decently
    0.82
     moderately
    0.81
     enough
    0.81
     adequate
    0.79
     wystar
    0.78
    Activations Density 0.088%

    No Known Activations